北京通用人工智能研究院BIGAI

科研成果

In Situ 3D Scene Synthesis for Ubiquitous Embodied Interfaces

Dynamic Planning for Sequential Whole-body Mobile Manipulation

Simulating Thin Shells by Bicubic Hermite Elements

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge

Varying Sentence Representations via Condition-Specified Routers

Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL